paper-with-me

홈 › Papers

Self-Supervised Learning of Phenotypic Representations from Cell Images with Weak Labels

2022-09-16 · Jan Oscar Cross-Zamirski, Guy Williams, Elizabeth Mouchet, Carola-Bibiane Schönlieb, Riku Turkki, Yinhai Wang

We propose WS-DINO as a novel framework to use weak label information in learning phenotypic representations from high-content fluorescent images of cells. Our model is based on a knowledge distillation approach with a vision transformer backbone (DINO), and we use this as a benchmark model for our study. Using WS-DINO, we fine-tuned with weak label information available in high-content microscopy screens (treatment and compound) and achieve state-of-the-art performance in not-same-compound mechanism of action prediction on the BBBC021 dataset (98%), and not-same-compound-and-batch performance (96%) using the compound as the weak label. Our method bypasses single cell cropping as a pre-processing step, and using self-attention maps we show that the model learns structurally meaningful phenotypic profiles.

📄 PDF Abstract BibTeX arXiv:2209.07819

Code (1)

crosszamirski/ws-dino 공식 구현 pytorch

Tasks

Knowledge DistillationSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

Contrastive Learning of Single-Cell Phenotypic Representations for Treatment Classification

2021-03-30 · Alexis Perakis, Ali Gorji, Samriddhi Jain, Krishna Chaitanya 외

Learning robust representations to discriminate cell phenotypes based on microscopy images is important for drug discovery. Drug development efforts typically analyse thousands of cell images to screen for potential trea…

Action ClassificationClassificationContrastive LearningDrug Discovery+1

Analysis of Cellular Feature Differences of Astrocytomas with Distinct Mutational Profiles Using Digitized Histopathology Images

2018-06-24 · Mousumi Roy, Fusheng Wang, George Teodoro, Jose Velazqeuz Vega 외

Cellular phenotypic features derived from histopathology images are the basis of pathologic diagnosis and are thought to be related to underlying molecular profiles. Due to overwhelming cell numbers and population hetero…

ClusteringDimensionality Reduction

Efficient Cell Painting Image Representation Learning via Cross-Well Aligned Masked Siamese Network

2025-09-24 · Pin-Jui Huang, Yu-Hsuan Liao, SooHeon Kim, NoSeong Park 외 arxiv

Computational models that predict cellular phenotypic responses to chemical and genetic perturbations can accelerate drug discovery by prioritizing therapeutic hypotheses and reducing costly wet-lab iteration. However, e…

Representation LearningContrastive LearningDrug Discovery

CellSymphony: Deciphering the molecular and phenotypic orchestration of cells with single-cell pathomics

2025-08-13 · Paul H. Acosta, Pingjun Chen, Simon P. Castillo, Maria Esther Salvatierra 외 arxiv

Xenium, a new spatial transcriptomics platform, enables subcellular-resolution profiling of complex tumor tissues. Despite the rich morphological information in histology images, extracting robust cell-level features and…

Comparing representations of biological data learned with different AI paradigms, augmenting and cropping strategies

2022-03-07 · Andrei Dmitrenko, Mauro M. Masiero, Nicola Zamboni

Recent advances in computer vision and robotics enabled automated large-scale biological image analysis. Various machine learning approaches have been successfully applied to phenotypic profiling. However, it remains unc…

Contrastive LearningRepresentation Learning